curl --request POST \
--url https://api.tikway.ai/v1/audio/speech \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "qwen3-tts-flash",
"input": "你好，欢迎使用语音合成。",
"voice": "Cherry"
}
'data: {"type":"speech.audio.delta","audio":"UklGRigAAABXQVZFZm10IBAAAAABAAEAwF0AAIC7AAACABAAZGF0YQQAAAAAAAEA"}
data: {"type":"speech.audio.done","usage":{"input_tokens":0,"output_tokens":0,"total_tokens":0,"characters":12}}
{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"param": "<string>"
}
}Qwen3-TTS
Qwen - 文转语音
通过 POST /v1/audio/speech 调用 Qwen3-TTS，返回 WAV 或统一 SSE 音频事件。语言扩展可放在 extra_body 或 body 顶层，顶层同名字段优先。模型 ID 或别名需已在目标平台配置。
POST
https://api.tikway.ai
/
v1
/
audio
/
speech
curl --request POST \
--url https://api.tikway.ai/v1/audio/speech \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "qwen3-tts-flash",
"input": "你好，欢迎使用语音合成。",
"voice": "Cherry"
}
'data: {"type":"speech.audio.delta","audio":"UklGRigAAABXQVZFZm10IBAAAAABAAEAwF0AAIC7AAACABAAZGF0YQQAAAAAAAEA"}
data: {"type":"speech.audio.done","usage":{"input_tokens":0,"output_tokens":0,"total_tokens":0,"characters":12}}
{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"param": "<string>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>",
"param": "<string>"
}
}授权
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
请求体
application/json
使用平台标准 model、字符串 input 和 voice 调用 Qwen3-TTS，固定返回 WAV 音频。语言可放入 extra_body 或顶层，同名字段顶层优先。
网关已配置的 Qwen3-TTS-Flash 模型 ID 或别名。
Minimum string length:
1示例:
"qwen3-tts-flash"
"bailian/qwen3-tts-flash"
需要合成的朗读文本，最多 600 字符，支持多语种混合输入。
Required string length:
1 - 600示例:
"你好，欢迎测试语音合成接口。"
填写 Qwen3-TTS 支持的预置音色，区分大小写；完整清单见 Qwen 音色指南。
Minimum string length:
1示例:
"Cherry"
"Serena"
"Ethan"
Qwen3-TTS 固定返回 WAV；省略时使用 WAV。
可用选项:
wav audio 返回 WAV 音频字节；sse 返回网关统一的 speech.audio.delta 和 speech.audio.done 事件，音频分片为 Base64。
可用选项:
audio, sse 兼容顶层扩展写法；与 extra_body.language_type 同时存在时，以此字段为准。通常只需选择一种位置传入。
可用选项:
Auto, Chinese, English, German, Italian, Portuguese, Spanish, Japanese, Korean, French, Russian 响应
音频字节或统一 SSE 音频事件；支持的媒体类型见下方列表。
The response is of type string.